Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 5319
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the letter "V" combined with numbers representing potential community affiliations or cultural elements (e.g., V9 may refer to a specific group or location)

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or concept denoted by "V"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ģĸ
    -0.72
    ãĥ¼ãĥĨ
    -0.65
     Heist
    -0.64
    dress
    -0.64
    ¯¯
    -0.64
     deduction
    -0.61
    ãĥ³ãĤ¸
    -0.60
     unrestricted
    -0.60
    manship
    -0.59
    ãĤ´ãĥ³
    -0.59
    POSITIVE LOGITS
    oodoo
    1.29
    ulture
    1.25
    arsity
    1.23
    IRT
    1.21
    isions
    1.19
    alky
    1.17
    ogue
    1.15
    ampires
    1.15
    odka
    1.13
    imeo
    1.09
    Activations Density 0.028%

    No Known Activations